Virtual Node Reconfiguration via Weighted Graph Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The challenge in cloud computing is the inefficiency and resource-intensiveness of reconfiguring computing clusters, particularly when adding or removing physical nodes, as it often requires moving virtual nodes, which is a time-consuming and resource-intensive process.
Innovation Solution
A cluster manager generates a data structure, such as a weighted bi-partite graph adjacency matrix, to determine a reconfiguration plan that minimizes the number of virtual node movements by maximizing weight matching, thereby optimizing the reconfiguration process without service interruptions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If virtual nodes are moved during reconfiguration of computing cluster, then the cluster can be reconfigured to add or remove physical nodes, but the reconfiguration process becomes time-consuming and resource-intensive
Solution Approach 1:
The patent applies preliminary action by pre-calculating and storing optimal virtual node assignment mappings in a data structure (such as a hash table or lookup table) before reconfiguration is needed. When reconfiguration occurs, the system retrieves the pre-computed optimal mapping rather than calculating it in real-time, significantly reducing reconfiguration time while maintaining adaptability to add or remove physical nodes
2Adaptability or versatility
If virtual nodes are moved during reconfiguration of computing cluster, then the cluster can be reconfigured to add or remove physical nodes, but the process becomes resource-intensive
Solution Approach 1:
The system performs resource-intensive calculations in advance to build optimization data structures that store pre-computed virtual node assignments. During actual reconfiguration, the system simply retrieves these pre-computed assignments, avoiding repeated resource-intensive calculations and minimizing energy consumption while maintaining full reconfiguration capability
Solution Approach 2:
The patent creates a data structure copy (such as a lookup table or cache) that stores optimal virtual node mappings. This copy allows the system to quickly retrieve and apply optimal assignments during reconfiguration without performing the full optimization calculation again, reducing resource consumption while preserving adaptability
3Adaptability or versatility
If virtual nodes are moved during reconfiguration of computing cluster, then the cluster can be reconfigured, but operational overhead increases
Solution Approach 1:
The system pre-computes and stores optimal virtual node assignments in data structures before reconfiguration is needed. This preliminary action simplifies the actual reconfiguration process to a simple lookup and application operation, reducing operational overhead while maintaining the ability to handle various reconfiguration scenarios
Solution Approach 2:
The patent introduces an intermediary data structure (such as a lookup table or cache) that mediates between the complex optimization problem and the simple reconfiguration execution. This intermediary stores pre-computed optimal mappings, allowing the system to handle complex reconfiguration scenarios through simple table lookups, thereby reducing operational overhead
Data Source
AI summary
Given a current configuration of virtual node groups in a computing cluster and a new configuration indicating one or more changes to the virtual node groups, a cluster manager generates a reconfiguration plan to arrange virtual nodes into the desired virtual node groups of the new configuration while minimizing a number of virtual nodes to be moved between physical nodes in the computing cluster.